Back to skill

Security audit

Personal Budget Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive budgeting guidance skill that stays local and does not access accounts, make transactions, or call external services.

Install this if you want local budgeting templates and lightweight recommendations. Treat outputs as informational, avoid sharing unnecessary sensitive financial details, and use a qualified professional for tax, investment, debt, or major financial decisions.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L18 states 'Clear documentation in English,' which imposes a specific language requirement in natural language. The file does not provide an opt-in choice or a documented justification for restricting output/documentation to English, which matches the locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The core description and several example sections are written in Chinese, which signals a language-specific experience, but the file does not state that the skill is intended only for Chinese-speaking users or offer any opt-in/choice of language. This can violate the language/locale policy because the skill appears generally applicable while implicitly constraining users to one language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section includes examples like receivables aging, invoice compliance, pricing strategy, tax deductions, and financial reports, which extend well beyond personal budgeting. This can cause the agent to activate in unintended financial-adjacent contexts and produce advice outside the skill’s stated scope, increasing the chance of misleading outputs or inappropriate routing.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module documentation says the skill is a 'Descriptive skill providing templates and frameworks,' implying generic guidance. In practice, the code parses user input for amounts, dates, debt, savings, retirement, timeframe, and priority, then generates individualized budgeting recommendations under the identity 'Personal Budget Planner,' which materially exceeds the documented intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes extremely broad terms such as "personal," "budget," and "planner," which are common in everyday conversation and likely to cause unintended invocation or routing collisions with other skills. In a finance-related skill, accidental activation can expose users to irrelevant budgeting prompts or capture sensitive financial context when the user did not intend to use this specific skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file declares language: en, but later includes a Chinese scenario and expected output without explaining whether the skill supports multiple languages or adapts to the user's language. This creates an unclear language policy and may amount to forcing or assuming a locale without explicit user opt-in or documented multilingual behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest sets the language to "en", which can indicate a fixed language choice. There is no visible note that this is user-selectable or justified as a region-specific constraint, so it may conflict with a language or locale choice policy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.